ClawHub
Back to skill

Security audit

artifact-publisher

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed HTML publishing and feedback tools, and the scanner warnings are unsupported by the inspected files.

Publishing uploads your HTML to an external service, and unlisted links can be opened by anyone who has them. Choose suitable access settings, protect your publisher key, and verify release readiness because the pack still carries dry-run notes.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/setup.md (reported line 15)May include surrounding context.

md
1. Register `https://app.artifactpublisher.com/mcp` as the remote MCP URL.
2. Complete consent in the browser (PKCE).
3. Never ask the user to paste an access token into chat.
4. Tokens stay in the client secret store.

Cursor example (`mcp.json` — URL only, no headers):

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/setup.md (reported line 18)May include surrounding context.

  1. Never ask the user to paste an access token into chat.
  2. Tokens stay in the client secret store.

Cursor example (mcp.json — URL only, no headers):

json
{

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/setup.md (reported line 15)May include surrounding context.

md
1. Register `https://app.artifactpublisher.com/mcp` as the remote MCP URL.
2. Complete consent in the browser (PKCE).
3. Never ask the user to paste an access token into chat.
4. Tokens stay in the client secret store.

Cursor example (`mcp.json` — URL only, no headers):

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.